Machine Translation Verbosity Control for Automatic Dubbing

TL;DR

This paper presents methods to control the verbosity of machine translation output to improve the quality of automatic dubbing, demonstrating benefits through both intrinsic and extrinsic evaluations on multiple languages.

Contribution

It introduces new techniques for MT verbosity control specifically tailored for automatic dubbing, enhancing translation alignment and dubbing quality.

Findings

Verbosity control improves dubbing synchronization

Proposed methods outperform state-of-the-art in intrinsic evaluations

Subjective tests show increased dubbing quality with verbosity control

Abstract

Automatic dubbing aims at seamlessly replacing the speech in a video document with synthetic speech in a different language. The task implies many challenges, one of which is generating translations that not only convey the original content, but also match the duration of the corresponding utterances. In this paper, we focus on the problem of controlling the verbosity of machine translation output, so that subsequent steps of our automatic dubbing pipeline can generate dubs of better quality. We propose new methods to control the verbosity of MT output and compare them against the state of the art with both intrinsic and extrinsic evaluations. For our experiments we use a public data set to dub English speeches into French, Italian, German and Spanish. Finally, we report extensive subjective tests that measure the impact of MT verbosity control on the final quality of dubbed video clips.